Files
TheRock/compiler/amd-llvm/llvm/test/CodeGen/AMDGPU/insert-delay-alu-attr.ll
T
derek.holloway 7502bf64a4
CodeQL / Analyze (actions) (push) Canceled after 0s
CodeQL / Analyze (python) (push) Canceled after 0s
pre-commit / pre-commit (push) Canceled after 0s
Multi-Arch CI / setup (push) Canceled after 0s
Publish build_manylinux_x86_64 images / publish_build_manylinux_x86_64 (push) Canceled after 0s
Setup (Multi-Arch) / setup (push) Canceled after 0s
Multi-Arch CI / Linux::${{ fromJSON(needs.setup.outputs.linux_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish no_rocm_image_ubi10 image / publish_no_rocm_image_ubi10 (push) Canceled after 0s
Multi-Arch CI / Windows::${{ fromJSON(needs.setup.outputs.windows_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Multi-Arch CI / Manifest Diff (push) Canceled after 0s
TheRock Manifest Diff Report / Generate Manifest Diff Report (push) Canceled after 0s
Multi-Arch CI / CI Summary (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04 (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04_ocl_rt images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04_rocgdb images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Unit Tests / Unit Tests :: ubuntu-24.04 (push) Canceled after 0s
Unit Tests / Unit Tests :: windows-2022 (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_media (push) Canceled after 0s
Unit Tests / Unit Tests Summary (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_openmpi (push) Canceled after 0s
Flatten subprojects into a single base monorepo
2026-09-02 16:34:47 -07:00

82 lines
3.5 KiB
LLVM

; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 6
; RUN: llc -mtriple=amdgcn -mcpu=gfx1250 < %s | FileCheck %s
define amdgpu_kernel void @delay_alu() {
; CHECK-LABEL: delay_alu:
; CHECK: ; %bb.0: ; %entry
; CHECK-NEXT: global_prefetch_b8 v0, s[0:1] scope:SCOPE_SE
; CHECK-NEXT: v_nop
; CHECK-NEXT: s_setreg_imm32_b32 hwreg(HW_REG_WAVE_MODE, 25, 1), 1 ; msbs: dst=0 src0=0 src1=0 src2=0
; CHECK-NEXT: v_and_b32_e32 v0, 0x3ff, v0
; CHECK-NEXT: s_delay_alu instid0(VALU_DEP_1) | instskip(NEXT) | instid1(VALU_DEP_1)
; CHECK-NEXT: v_add_nc_u32_e32 v0, 0xff, v0
; CHECK-NEXT: v_lshrrev_b32_e32 v0, 8, v0
; CHECK-NEXT: buffer_store_b32 v0, v0, s[0:3], null offen
; CHECK-NEXT: s_endpgm
entry:
%15 = tail call i32 @llvm.amdgcn.workitem.id.x()
%16 = add i32 %15, 255
%17 = sdiv i32 %16, 256
tail call void @llvm.amdgcn.raw.ptr.buffer.store.i32(i32 %17, ptr addrspace(8) poison, i32 poison, i32 0, i32 0)
ret void
}
define amdgpu_kernel void @delay_alu_waves_1_8() "amdgpu-waves-per-eu"="1,8" {
; CHECK-LABEL: delay_alu_waves_1_8:
; CHECK: ; %bb.0: ; %entry
; CHECK-NEXT: global_prefetch_b8 v0, s[0:1] scope:SCOPE_SE
; CHECK-NEXT: v_nop
; CHECK-NEXT: s_setreg_imm32_b32 hwreg(HW_REG_WAVE_MODE, 25, 1), 1 ; msbs: dst=0 src0=0 src1=0 src2=0
; CHECK-NEXT: v_and_b32_e32 v0, 0x3ff, v0
; CHECK-NEXT: s_delay_alu instid0(VALU_DEP_1) | instskip(NEXT) | instid1(VALU_DEP_1)
; CHECK-NEXT: v_add_nc_u32_e32 v0, 0xff, v0
; CHECK-NEXT: v_lshrrev_b32_e32 v0, 8, v0
; CHECK-NEXT: buffer_store_b32 v0, v0, s[0:3], null offen
; CHECK-NEXT: s_endpgm
entry:
%15 = tail call i32 @llvm.amdgcn.workitem.id.x()
%16 = add i32 %15, 255
%17 = sdiv i32 %16, 256
tail call void @llvm.amdgcn.raw.ptr.buffer.store.i32(i32 %17, ptr addrspace(8) poison, i32 poison, i32 0, i32 0)
ret void
}
define amdgpu_kernel void @delay_alu_waves_1_1() "amdgpu-waves-per-eu"="1,1" {
; CHECK-LABEL: delay_alu_waves_1_1:
; CHECK: ; %bb.0: ; %entry
; CHECK-NEXT: global_prefetch_b8 v0, s[0:1] scope:SCOPE_SE
; CHECK-NEXT: v_nop
; CHECK-NEXT: s_setreg_imm32_b32 hwreg(HW_REG_WAVE_MODE, 25, 1), 1 ; msbs: dst=0 src0=0 src1=0 src2=0
; CHECK-NEXT: v_and_b32_e32 v0, 0x3ff, v0
; CHECK-NEXT: s_delay_alu instid0(VALU_DEP_1) | instskip(NEXT) | instid1(VALU_DEP_1)
; CHECK-NEXT: v_add_nc_u32_e32 v0, 0xff, v0
; CHECK-NEXT: v_lshrrev_b32_e32 v0, 8, v0
; CHECK-NEXT: buffer_store_b32 v0, v0, s[0:3], null offen
; CHECK-NEXT: s_endpgm
entry:
%15 = tail call i32 @llvm.amdgcn.workitem.id.x()
%16 = add i32 %15, 255
%17 = sdiv i32 %16, 256
tail call void @llvm.amdgcn.raw.ptr.buffer.store.i32(i32 %17, ptr addrspace(8) poison, i32 poison, i32 0, i32 0)
ret void
}
define amdgpu_kernel void @delay_alu_waves_1_1_wgsize() "amdgpu-flat-work-group-size"="1,128" "amdgpu-waves-per-eu"="1,1" {
; CHECK-LABEL: delay_alu_waves_1_1_wgsize:
; CHECK: ; %bb.0: ; %entry
; CHECK-NEXT: global_prefetch_b8 v0, s[0:1] scope:SCOPE_SE
; CHECK-NEXT: v_nop
; CHECK-NEXT: s_setreg_imm32_b32 hwreg(HW_REG_WAVE_MODE, 25, 1), 1 ; msbs: dst=0 src0=0 src1=0 src2=0
; CHECK-NEXT: v_and_b32_e32 v0, 0x3ff, v0
; CHECK-NEXT: v_add_nc_u32_e32 v0, 0xff, v0
; CHECK-NEXT: v_lshrrev_b32_e32 v0, 8, v0
; CHECK-NEXT: buffer_store_b32 v0, v0, s[0:3], null offen
; CHECK-NEXT: s_endpgm
entry:
%15 = tail call i32 @llvm.amdgcn.workitem.id.x()
%16 = add i32 %15, 255
%17 = sdiv i32 %16, 256
tail call void @llvm.amdgcn.raw.ptr.buffer.store.i32(i32 %17, ptr addrspace(8) poison, i32 poison, i32 0, i32 0)
ret void
}